CN112508969B - Tubular structure segmentation graph fracture repair system of three-dimensional image based on deep learning network - Google Patents
Tubular structure segmentation graph fracture repair system of three-dimensional image based on deep learning network Download PDFInfo
- Publication number
- CN112508969B CN112508969B CN202011457993.7A CN202011457993A CN112508969B CN 112508969 B CN112508969 B CN 112508969B CN 202011457993 A CN202011457993 A CN 202011457993A CN 112508969 B CN112508969 B CN 112508969B
- Authority
- CN
- China
- Prior art keywords
- learning network
- deep learning
- graph
- segmentation
- target organ
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/11—Region-based segmentation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
- G06T7/0012—Biomedical image inspection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10004—Still image; Photographic image
- G06T2207/10012—Stereo images
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20081—Training; Learning
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20084—Artificial neural networks [ANN]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30004—Biomedical image processing
- G06T2207/30101—Blood vessel; Artery; Vein; Vascular
Landscapes
- Engineering & Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- Nuclear Medicine, Radiotherapy & Molecular Imaging (AREA)
- Radiology & Medical Imaging (AREA)
- Quality & Reliability (AREA)
- Image Analysis (AREA)
- Image Processing (AREA)
Abstract
The embodiment of the invention provides a tubular structure segmentation graph fracture repairing system of a three-dimensional image based on a deep learning network, which comprises: a preprocessing module: the system is used for preprocessing the three-dimensional image data; an image resampling module: the system comprises a preprocessing unit, a data processing unit and a data processing unit, wherein the preprocessing unit is used for preprocessing three-dimensional image data; a target organ extraction module: the three-dimensional data of all candidate sensing areas are input into a target segmentation depth learning network to obtain a target organ segmentation map in each interested area; a fracture repair module: the device is used for carrying out distance conversion on the target organ segmentation graph to obtain a distance conversion graph, inputting the target organ segmentation graph and the distance conversion graph into a fracture repair deep learning network together to obtain a fracture repair graph of each region of interest, and splicing and combining all the fracture repair graphs together to obtain a complete target organ segmentation result. The system can realize automatic fracture repair and improve the segmentation effect.
Description
Technical Field
The invention relates to the field of medical images, in particular to a tubular structure segmentation graph fracture repairing system of a three-dimensional image based on a deep learning network.
Background
In normal human anatomy, there are many organs of tubular structure, such as arteries, veins, bronchi, nerves, and so on. In the process of disease diagnosis and treatment, the reconstruction of these organs is very important and has important clinical value.
At present, abnormal conditions such as noise, fracture and the like can occur in a segmentation image after automatic reconstruction aiming at different tubular organs, and the diagnosis and treatment of diseases are seriously influenced.
The information disclosed in this background section is only for enhancement of understanding of the general background of the invention and should not be taken as an acknowledgement or any form of suggestion that this information forms the prior art already known to a person skilled in the art.
Disclosure of Invention
Aiming at the problems in the prior art, the embodiment of the invention provides a tubular structure segmentation graph fracture repairing system of a three-dimensional image based on a deep learning network.
In a first aspect, an embodiment of the present invention provides a tubular structure segmentation map fracture repairing method for a three-dimensional image based on a deep learning network, including the following steps:
step S1: collecting three-dimensional image data and preprocessing the three-dimensional image data;
step S2: resampling the preprocessed three-dimensional image data to generate a plurality of candidate three-dimensional data of the interested region;
step S3: inputting the three-dimensional data of all candidate sensing areas into a target segmentation deep learning network to obtain a target organ segmentation map in each interested area;
step S4: and performing distance transformation on the target organ segmentation graph to obtain a distance transformation graph, inputting the target organ segmentation graph and the distance transformation graph 1 into a fracture repair deep learning network to obtain a fracture repair graph of each region of interest, and splicing and combining all the fracture repair graphs together to obtain a complete target organ segmentation result.
Further, the preprocessing of the three-dimensional image data in step S1 includes the steps of: pixel value normalization and interpolation.
Further, the method for normalizing the pixel value comprises the following steps:
min=c-w/2
max=c+w/2
if x<min then x=0
if x>max then x=1
where c is the window level, w is the window width, and x is the pixel value.
Further, the interpolation method comprises the following steps: analyzing an original three-dimensional image to obtain an image Spacing attribute (z)0,y0,x0) (ii) a Wherein the target image Spacing is (z)1,y1,x1) Calculating a scaling factor (z) for each direction0/z1,y0/y1,x0/x1) And then, obtaining the interpolated three-dimensional data by utilizing bilinear interpolation according to the scaling factors of all directions.
Further, the resampling method in step S2 is: the three-dimensional data after interpolation is extracted into a three-dimensional image of partial patches which are 64 × 96 × 96 and overlap each other according to the step size of 32 × 48 × 48.
Further, the target segmentation deep learning network alternately performs 4 times by using a convolution residual block and down sampling to extract high-dimensional features, and then alternately performs 4 times by using the convolution residual block and up sampling to restore the resolution of the original input image.
Further, the feature map of the target segmentation deep learning network after the up-sampling is fused with the feature map of the low-level same resolution.
Further, the target segmentation deep learning network performs feature fusion on target organ feature maps with different depths by means of upsampling.
Further, the fracture repairing deep learning network alternately performs 1 time by utilizing a convolution residual block and down sampling to extract high-dimensional features, and then alternately performs 1 time by utilizing the convolution residual block and up sampling to restore the resolution of the original input image.
In a second aspect, an embodiment of the present invention provides a tubular structure segmentation graph fracture repair system for a three-dimensional image based on a deep learning network, including:
a preprocessing module: the system is used for preprocessing the three-dimensional image data;
an image resampling module: the system comprises a preprocessing unit, a data processing unit and a data processing unit, wherein the preprocessing unit is used for preprocessing three-dimensional image data;
a target organ extraction module: the three-dimensional data of all candidate sensing areas are input into a target segmentation deep learning network to obtain a target organ segmentation map in each interested area;
a fracture repair module: the method is used for performing distance conversion on the target organ segmentation graph to obtain a distance conversion graph, inputting the target organ segmentation graph and the distance conversion graph 1 into a fracture repair deep learning network to obtain a fracture repair graph of each region of interest, and splicing and combining all the fracture repair graphs together to obtain a complete target organ segmentation result.
The tubular structure segmentation graph fracture repairing system of the three-dimensional image based on the deep learning network provided by the embodiment of the invention has the following advantages: the tubular structure segmentation map fracture repairing method and system for the three-dimensional image utilize distance transformation information of the fracture part as fracture position identification information, and automatic fracture repairing can be achieved without detecting the fracture position in advance, so that the method and system are simple and effective, and the segmentation effect is improved.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, and it is obvious that the drawings in the following description are some embodiments of the present invention, and those skilled in the art can also obtain other drawings according to the drawings without creative efforts.
Fig. 1 is a flowchart of a tubular structure segmentation graph fracture repairing method for a three-dimensional image based on a deep learning network according to an embodiment of the present invention;
fig. 2 is a schematic structural diagram of a target segmentation deep learning network in the method according to the embodiment of the present invention;
fig. 3 is a schematic structural diagram of a fracture repair deep learning network in the method according to the embodiment of the present invention;
fig. 4 is a schematic diagram of a tubular structure segmentation graph fracture repair system for a three-dimensional image based on a deep learning network according to an embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are some, but not all, embodiments of the present invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
Throughout the specification and claims, unless explicitly stated otherwise, the word "comprise", or variations such as "comprises" or "comprising", will be understood to imply the inclusion of a stated element or component but not the exclusion of any other element or component.
Fig. 1 is a flowchart of a tubular structure segmentation graph fracture repair method for a three-dimensional image based on a deep learning network according to an embodiment of the present invention, and as shown in fig. 1, the tubular structure segmentation graph fracture repair method for a three-dimensional image based on a deep learning network according to the present invention includes the following steps:
step S1: collecting three-dimensional image data and preprocessing the three-dimensional image data;
in step S1 of the embodiment of the present invention, the preprocessing of the three-dimensional image data includes the following steps: pixel value normalization and interpolation.
The pixel value normalization method comprises the following steps:
min=c-w/2
max=c+w/2
if x<min then x=0
if x>max then x=1
where c is the window level, w is the window width, and x is the pixel value.
The interpolation method comprises the following steps: first, analyze original threeDimension image, obtaining image Spacing attribute (z)0,y0,x0) (ii) a Wherein the target image Spacing is (z)1,y1,x1) Calculating a scaling factor (z) for each direction0/z1,y0/y1,x0/x1) And then, obtaining the interpolated three-dimensional data by utilizing bilinear interpolation according to the scaling factors of all directions.
Step S2: resampling the preprocessed three-dimensional image data to generate a plurality of candidate three-dimensional data of the interested region;
in step S2 of the embodiment of the present invention, the resampling method includes: the three-dimensional data after interpolation is extracted into a three-dimensional image of partial patches which are 64 × 96 × 96 and overlap each other according to the step size of 32 × 48 × 48.
Step S3: inputting the three-dimensional data of all candidate sensing areas into a target segmentation deep learning network to obtain a target organ segmentation map in each interested area;
step S4: and performing distance transformation on the target organ segmentation graph to obtain a distance transformation graph, inputting the target organ segmentation graph and the distance transformation graph 1 into a fracture repair deep learning network to obtain a fracture repair graph of each region of interest, and splicing and combining all the fracture repair graphs together to obtain a complete target organ segmentation result.
The deep learning network of the three-dimensional image arteriovenous segmentation method adopts two-stage identification of a target segmentation deep learning network and a fracture repair deep learning network, namely, the target segmentation deep learning network is used for extracting a target organ to obtain a target organ segmentation graph, the target organ segmentation graph is subjected to distance conversion to obtain a distance conversion graph, and the target organ segmentation graph and the distance conversion graph 1 are input into the fracture repair deep learning network for fracture repair.
The target segmentation deep learning network and the fracture repair deep learning network are output probability graphs.
As shown in fig. 2, the target segmentation deep learning network alternately performs 4 times of convolution residual block and down-sampling to extract high-dimensional features, and then alternately performs 4 times of convolution residual block and up-sampling to restore to the resolution of the original input image.
In order to supplement information related to positions of a low level, the feature map of the target segmentation deep learning network after up-sampling is fused with the feature map of the low level with the same resolution.
In order to strengthen the attention of target organs with different sizes, the target segmentation deep learning network performs feature fusion on target organ feature maps with different depths by means of upsampling.
As shown in fig. 3, the fracture repair deep learning network alternately performs 1 time of convolution residual block and down-sampling to extract high-dimensional features, and then alternately performs 1 time of convolution residual block and up-sampling to restore the resolution of the original input image.
In order to enlarge the receptive field and capture multi-scale features, the fracture repair deep learning network uses a scaled convolution in the residual blocks of 4 th, 5 th, 6 th, 7 th and 8 th; and supplementing the low-level detail information by using skip connection.
Based on any of the above embodiments, fig. 4 is a schematic structural diagram of a tubular structure segmentation graph fracture repair system for a three-dimensional image based on a deep learning network according to an embodiment of the present invention, where the system includes:
a preprocessing module: the system is used for preprocessing the three-dimensional image data;
an image resampling module: the system comprises a preprocessing unit, a data processing unit and a data processing unit, wherein the preprocessing unit is used for preprocessing three-dimensional image data;
a target organ extraction module: the three-dimensional data of all candidate sensing areas are input into a target segmentation deep learning network to obtain a target organ segmentation map in each interested area;
a fracture repair module: the method is used for performing distance conversion on the target organ segmentation graph to obtain a distance conversion graph, inputting the target organ segmentation graph and the distance conversion graph 1 into a fracture repair deep learning network to obtain a fracture repair graph of each region of interest, and splicing and combining all the fracture repair graphs together to obtain a complete target organ segmentation result.
In summary, the tubular structure segmentation map fracture repair system based on the three-dimensional image of the deep learning network provided by the embodiment of the invention uses the distance transformation information of the fracture as the fracture position identification information, and can realize automatic fracture repair without detecting the fracture position in advance, so that the method is simple and effective, and the segmentation effect is improved.
The above-described embodiments of the apparatus are merely illustrative, and the units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of the present embodiment. One of ordinary skill in the art can understand and implement it without inventive effort.
Through the above description of the embodiments, those skilled in the art will clearly understand that each embodiment can be implemented by software plus a necessary general hardware platform, and certainly can also be implemented by hardware. With this understanding in mind, the above-described technical solutions may be embodied in the form of a software product, which can be stored in a computer-readable storage medium such as ROM/RAM, magnetic disk, optical disk, etc., and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute the methods described in the embodiments or some parts of the embodiments.
Finally, it should be noted that: the above examples are only intended to illustrate the technical solution of the present invention, but not to limit it; although the present invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; and such modifications or substitutions do not depart from the spirit and scope of the corresponding technical solutions of the embodiments of the present invention.
Claims (1)
1. A tubular structure segmentation graph fracture repairing system of a three-dimensional image based on a deep learning network is characterized by comprising:
a preprocessing module: the system is used for preprocessing the three-dimensional image data;
an image resampling module: the system comprises a preprocessing unit, a data processing unit and a data processing unit, wherein the preprocessing unit is used for preprocessing three-dimensional image data;
a target organ extraction module: the three-dimensional data of all candidate sensing areas are input into a target segmentation deep learning network to obtain a target organ segmentation map in each interested area; the target segmentation deep learning network alternately performs 4 times by using a convolution residual block and down sampling to extract high-dimensional features, and then alternately performs 4 times by using the convolution residual block and up sampling to restore the resolution of the original input image; the feature map of the target segmentation deep learning network after up-sampling is fused with the feature map of the low level with the same resolution; the target segmentation deep learning network performs feature fusion on target organ feature maps at different depths by utilizing upsampling;
a fracture repair module: the system comprises a distance transformation graph, a fracture restoration deep learning network and a target organ segmentation graph, wherein the distance transformation graph is used for carrying out distance transformation on a target organ segmentation graph to obtain a distance transformation graph, the target organ segmentation graph and the distance transformation graph are input into the fracture restoration deep learning network together to obtain a fracture restoration graph of each region of interest, and all the fracture restoration graphs are spliced and combined together to obtain a complete target organ segmentation result; the fracture repairing deep learning network alternately performs 1 time by using a convolution residual block and down sampling to extract high-dimensional features, and then alternately performs 1 time by using the convolution residual block and up sampling to restore the resolution of the original input image; the fracture repair deep learning network uses a scaled convolution in the residual blocks of 4 th, 5 th, 6 th, 7 th and 8 th; and supplementing the low-level detail information by using skip connection.
Priority Applications (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202011457993.7A CN112508969B (en) | 2020-02-18 | 2020-02-18 | Tubular structure segmentation graph fracture repair system of three-dimensional image based on deep learning network |
PCT/CN2020/139471 WO2021164418A1 (en) | 2020-02-18 | 2020-12-25 | Tubular structure segmentation map fracture restoration system for three-dimensional image based on deep learning network |
Applications Claiming Priority (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010098343.1A CN111260670B (en) | 2020-02-18 | 2020-02-18 | Tubular structure segmentation graph fracture repairing method and system of three-dimensional image based on deep learning network |
CN202011457993.7A CN112508969B (en) | 2020-02-18 | 2020-02-18 | Tubular structure segmentation graph fracture repair system of three-dimensional image based on deep learning network |
Related Parent Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202010098343.1A Division CN111260670B (en) | 2020-02-18 | 2020-02-18 | Tubular structure segmentation graph fracture repairing method and system of three-dimensional image based on deep learning network |
Publications (2)
Publication Number | Publication Date |
---|---|
CN112508969A CN112508969A (en) | 2021-03-16 |
CN112508969B true CN112508969B (en) | 2021-12-07 |
Family
ID=70952766
Family Applications (2)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202011457993.7A Active CN112508969B (en) | 2020-02-18 | 2020-02-18 | Tubular structure segmentation graph fracture repair system of three-dimensional image based on deep learning network |
CN202010098343.1A Active CN111260670B (en) | 2020-02-18 | 2020-02-18 | Tubular structure segmentation graph fracture repairing method and system of three-dimensional image based on deep learning network |
Family Applications After (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202010098343.1A Active CN111260670B (en) | 2020-02-18 | 2020-02-18 | Tubular structure segmentation graph fracture repairing method and system of three-dimensional image based on deep learning network |
Country Status (2)
Country | Link |
---|---|
CN (2) | CN112508969B (en) |
WO (2) | WO2021164418A1 (en) |
Families Citing this family (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112508969B (en) * | 2020-02-18 | 2021-12-07 | 广州柏视医疗科技有限公司 | Tubular structure segmentation graph fracture repair system of three-dimensional image based on deep learning network |
CN113808146B (en) * | 2021-10-18 | 2023-08-18 | 山东大学 | Multi-organ segmentation method and system for medical image |
CN114049359B (en) * | 2021-11-22 | 2024-04-16 | 北京航空航天大学 | Medical image organ segmentation method |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
KR101754291B1 (en) * | 2017-04-04 | 2017-07-06 | 이현섭 | Medical image processing system and method for personalized brain disease diagnosis and status determination |
CN109448005A (en) * | 2018-10-31 | 2019-03-08 | 数坤(北京)网络科技有限公司 | One kind being used for network model dividing method coronarius and equipment |
CN109934816A (en) * | 2019-03-21 | 2019-06-25 | 数坤(北京)网络科技有限公司 | A kind of method of complementation model, equipment and computer readable storage medium |
CN110287956A (en) * | 2019-06-13 | 2019-09-27 | 北京理工大学 | Vessel centerline automatic matching method and device |
CN110570446A (en) * | 2019-09-20 | 2019-12-13 | 河南工业大学 | Fundus retina image segmentation method based on generation countermeasure network |
Family Cites Families (18)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US6785409B1 (en) * | 2000-10-24 | 2004-08-31 | Koninklijke Philips Electronics, N.V. | Segmentation method and apparatus for medical images using diffusion propagation, pixel classification, and mathematical morphology |
US20080159604A1 (en) * | 2005-12-30 | 2008-07-03 | Allan Wang | Method and system for imaging to identify vascularization |
CN103295195B (en) * | 2013-05-16 | 2017-07-07 | 深圳市旭东数字医学影像技术有限公司 | The enhanced method of vascular and its system of soft image |
CN106204733B (en) * | 2016-07-22 | 2024-04-19 | 青岛大学附属医院 | Liver and kidney CT image combined three-dimensional construction system |
JP7184489B2 (en) * | 2016-09-18 | 2022-12-06 | イェダ リサーチ アンド ディベロップメント カンパニー リミテッド | Systems and methods for generating 3D images based on fluorescent illumination |
US10709399B2 (en) * | 2017-11-30 | 2020-07-14 | Shenzhen Keya Medical Technology Corporation | Methods and devices for performing three-dimensional blood vessel reconstruction using angiographic images |
US11335464B2 (en) * | 2018-01-12 | 2022-05-17 | Siemens Medical Solutions Usa, Inc. | Integrated precision medicine by combining quantitative imaging techniques with quantitative genomics for improved decision making |
CN109523507B (en) * | 2018-09-26 | 2023-09-19 | 苏州六莲科技有限公司 | Method and device for generating lesion image and computer readable storage medium |
CN109377458B (en) * | 2018-09-30 | 2020-06-12 | 数坤(北京)网络科技有限公司 | Method and device for repairing coronary artery segmentation fracture |
CN109583576B (en) * | 2018-12-17 | 2020-11-06 | 上海联影智能医疗科技有限公司 | Medical image processing device and method |
CN109903292A (en) * | 2019-01-24 | 2019-06-18 | 西安交通大学 | A kind of three-dimensional image segmentation method and system based on full convolutional neural networks |
CN109785325A (en) * | 2019-01-30 | 2019-05-21 | 陕西中医药大学 | A method of the Multimodal medical image based on deep learning |
CN109934812B (en) * | 2019-03-08 | 2022-12-09 | 腾讯科技(深圳)有限公司 | Image processing method, image processing apparatus, server, and storage medium |
CN109961446B (en) * | 2019-03-27 | 2021-06-01 | 深圳视见医疗科技有限公司 | CT/MR three-dimensional image segmentation processing method, device, equipment and medium |
CN110288524B (en) * | 2019-05-09 | 2020-10-30 | 广东启迪图卫科技股份有限公司 | Deep learning super-resolution method based on enhanced upsampling and discrimination fusion mechanism |
CN110599465B (en) * | 2019-08-28 | 2022-07-26 | 上海联影智能医疗科技有限公司 | Image positioning method and device, computer equipment and storage medium |
CN110765856B (en) * | 2019-09-12 | 2022-08-12 | 南京邮电大学 | Convolution-based low-quality finger vein image edge detection algorithm |
CN112508969B (en) * | 2020-02-18 | 2021-12-07 | 广州柏视医疗科技有限公司 | Tubular structure segmentation graph fracture repair system of three-dimensional image based on deep learning network |
-
2020
- 2020-02-18 CN CN202011457993.7A patent/CN112508969B/en active Active
- 2020-02-18 CN CN202010098343.1A patent/CN111260670B/en active Active
- 2020-12-25 WO PCT/CN2020/139471 patent/WO2021164418A1/en active Application Filing
- 2020-12-25 WO PCT/CN2020/139468 patent/WO2021164417A1/en active Application Filing
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
KR101754291B1 (en) * | 2017-04-04 | 2017-07-06 | 이현섭 | Medical image processing system and method for personalized brain disease diagnosis and status determination |
CN109448005A (en) * | 2018-10-31 | 2019-03-08 | 数坤(北京)网络科技有限公司 | One kind being used for network model dividing method coronarius and equipment |
CN109934816A (en) * | 2019-03-21 | 2019-06-25 | 数坤(北京)网络科技有限公司 | A kind of method of complementation model, equipment and computer readable storage medium |
CN110287956A (en) * | 2019-06-13 | 2019-09-27 | 北京理工大学 | Vessel centerline automatic matching method and device |
CN110570446A (en) * | 2019-09-20 | 2019-12-13 | 河南工业大学 | Fundus retina image segmentation method based on generation countermeasure network |
Also Published As
Publication number | Publication date |
---|---|
WO2021164417A1 (en) | 2021-08-26 |
CN111260670A (en) | 2020-06-09 |
CN111260670B (en) | 2021-02-19 |
WO2021164418A1 (en) | 2021-08-26 |
CN112508969A (en) | 2021-03-16 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN109949309B (en) | Liver CT image segmentation method based on deep learning | |
CN112508969B (en) | Tubular structure segmentation graph fracture repair system of three-dimensional image based on deep learning network | |
CN109410219B (en) | Image segmentation method and device based on pyramid fusion learning and computer readable storage medium | |
CN112950651B (en) | Automatic delineation method of mediastinal lymph drainage area based on deep learning network | |
CN110544205B (en) | Image super-resolution reconstruction method based on visible light and infrared cross input | |
CN110473243B (en) | Tooth segmentation method and device based on depth contour perception and computer equipment | |
CN111127482A (en) | CT image lung trachea segmentation method and system based on deep learning | |
CN113012155A (en) | Bone segmentation method in hip image, electronic device, and storage medium | |
CN112446892A (en) | Cell nucleus segmentation method based on attention learning | |
CN109948575B (en) | Eyeball area segmentation method in ultrasonic image | |
CN111815766A (en) | Processing method and system for reconstructing blood vessel three-dimensional model based on 2D-DSA image | |
CN116228785A (en) | Pneumonia CT image segmentation method based on improved Unet network | |
CN113299363A (en) | Yoov 5-based dermatology over-the-counter medicine selling method | |
CN112700460A (en) | Image segmentation method and system | |
Wang et al. | Automatic consecutive context perceived transformer GAN for serial sectioning image blind inpainting | |
CN117876836A (en) | Image fusion method based on multi-scale feature extraction and target reconstruction | |
CN111325756A (en) | Three-dimensional image artery and vein segmentation method and system based on deep learning network | |
CN112734638B (en) | Remote sensing image super-resolution reconstruction method and device and storage medium | |
CN117409002A (en) | Visual identification detection system for wounds and detection method thereof | |
CN114170221B (en) | Method and system for confirming brain diseases based on images | |
CN115565034A (en) | Infrared small target detection method based on double-current enhanced network | |
CN113177938B (en) | Method and device for segmenting brain glioma based on circular convolution kernel and related components | |
CN111462067B (en) | Image segmentation method and device | |
CN112529949A (en) | Method and system for generating DWI image based on T2 image | |
CN116824139B (en) | Endoscope polyp segmentation method based on boundary supervision and time sequence association |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant |